{"id":"https://openalex.org/W7131118646","doi":"https://doi.org/10.1109/iccvw69036.2025.00305","title":"Multi-Scale Hybrid CNN-Transformer for Smoke Detection in Satellite Images","display_name":"Multi-Scale Hybrid CNN-Transformer for Smoke Detection in Satellite Images","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131118646","doi":"https://doi.org/10.1109/iccvw69036.2025.00305"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051547647","display_name":"Tony Zhang","orcid":"https://orcid.org/0009-0009-0288-8270"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tony Zhang","raw_affiliation_strings":["University of Michigan,Ann Arbor,MI,48109"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI,48109","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111968870","display_name":"R P Dick","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Dick","raw_affiliation_strings":["University of Michigan,Ann Arbor,MI,48109"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI,48109","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051547647"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":1.4827,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87407851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2920","last_page":"2926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12597","display_name":"Fire Detection and Safety Systems","score":0.9584000110626221,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12597","display_name":"Fire Detection and Safety Systems","score":0.9584000110626221,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.011500000022351742,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12406","display_name":"IoT and GPS-based Vehicle Safety Systems","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5539000034332275},{"id":"https://openalex.org/keywords/smoke","display_name":"Smoke","score":0.53329998254776},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43869999051094055},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4375999867916107},{"id":"https://openalex.org/keywords/satellite-image","display_name":"Satellite image","score":0.41290000081062317},{"id":"https://openalex.org/keywords/satellite","display_name":"Satellite","score":0.3788999915122986},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3621000051498413},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3578999936580658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408000230789185},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5539000034332275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5351999998092651},{"id":"https://openalex.org/C58874564","wikidata":"https://www.wikidata.org/wiki/Q130768","display_name":"Smoke","level":2,"score":0.53329998254776},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C2985301230","wikidata":"https://www.wikidata.org/wiki/Q725252","display_name":"Satellite image","level":3,"score":0.41290000081062317},{"id":"https://openalex.org/C19269812","wikidata":"https://www.wikidata.org/wiki/Q26540","display_name":"Satellite","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.37720000743865967},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3621000051498413},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3483000099658966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C108597893","wikidata":"https://www.wikidata.org/wiki/Q663650","display_name":"Reflectivity","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2778102629","wikidata":"https://www.wikidata.org/wiki/Q725252","display_name":"Satellite imagery","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2621000111103058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2013300501","https://openalex.org/W2089926733","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2919981789","https://openalex.org/W2956265248","https://openalex.org/W2963446712","https://openalex.org/W2964169840","https://openalex.org/W3045923543","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W3199537137","https://openalex.org/W3207815352","https://openalex.org/W4312443924","https://openalex.org/W4385245566"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1,68],"addresses":[2],"the":[3,67,101,133],"challenge":[4],"of":[5,136],"smoke":[6,44,141],"detection":[7,142],"from":[8],"satellite":[9],"images,":[10],"which":[11],"is":[12,112,130],"crucial":[13],"for":[14,43,140],"identifying":[15],"and":[16,25,76,143],"mitigating":[17],"wildfires.":[18],"Smoke":[19],"can":[20],"vary":[21],"in":[22,49,53,119],"size,":[23],"shape,":[24],"texture,":[26],"making":[27],"it":[28],"difficult":[29],"to":[30,56,85,114],"classify":[31],"using":[32],"remote":[33,137],"sensing":[34,138],"images.":[35],"While":[36],"several":[37],"CNN":[38,75,106],"architectures":[39],"have":[40,47],"been":[41],"proposed":[42,128],"detection,":[45],"they":[46],"limitations":[48],"modeling":[50],"long-range":[51],"context":[52],"images":[54,139],"due":[55],"convolution's":[57],"bias":[58],"towards":[59],"learning":[60],"local":[61],"relationships.":[62],"To":[63],"address":[64],"this":[65],"limitation,":[66],"describes":[69],"a":[70],"hybrid":[71],"network":[72],"that":[73],"combines":[74],"transformer":[77,80,102,110],"architectures.":[78],"The":[79,127],"architecture":[81,103],"leverages":[82],"multi-head":[83],"attention":[84],"learn":[86],"long-range,":[87],"global":[88],"relationships":[89,116],"among":[90,117],"different":[91,120],"image":[92],"regions.":[93],"Initially,":[94],"multi-scale":[95],"features":[96,118],"are":[97],"extracted":[98],"by":[99],"adding":[100],"after":[104],"each":[105],"layer.":[107],"Additionally,":[108],"another":[109],"layer":[111],"appended":[113],"capture":[115],"receptive":[121],"fields,":[122],"significantly":[123],"improving":[124],"model":[125],"accuracy.":[126],"approach":[129],"evaluated":[131],"on":[132],"USTC_SmokeRS":[134],"dataset":[135],"outperforms":[144],"prior":[145],"methods.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2026-02-24T00:00:00"}